Many studies utilize dual-pixel (DP) sensor phase characteristics for various applications, such as depth estimation and deblurring. However, since the DP image features are entirely determined by the camera hardware, DP-depth paired datasets are very scarce, especially when performing depth estimation on customized cameras. To overcome this, studies simulate DP images using ideal optical system models. However, these simulations often violate real optical propagation laws, leading to poor generalization to real DP data. To address this, we investigate the domain gap between simulated and real DP data, and propose solutions using the Simulating DP images from ray tracing (Sdirt) scheme. The Sdirt generates realistic DP images via ray tracing and integrates them into the depth estimation training pipeline. Experimental results show that models trained with Sdirt-simulated images generalize better to real DP data. The code and collected datasets will be available at github.com/LinYark/Sdirt

翻译：许多研究利用双像素（DP）传感器的相位特性实现多种应用，例如深度估计与去模糊。然而，由于DP图像特征完全由相机硬件决定，DP-深度配对数据集非常稀缺，尤其是在针对定制相机进行深度估计时。为克服此问题，现有研究采用理想光学系统模型来模拟DP图像。然而，这些模拟往往违背真实的光学传播规律，导致对真实DP数据的泛化能力较差。为此，我们研究了模拟与真实DP数据之间的领域差异，并提出基于光线追踪的DP图像模拟（Sdirt）方案以解决该问题。Sdirt通过光线追踪生成逼真的DP图像，并将其整合至深度估计训练流程中。实验结果表明，使用Sdirt模拟图像训练的模型对真实DP数据具有更优的泛化性能。代码与收集的数据集将在github.com/LinYark/Sdirt公开。